Build notes: both upstream changes are merged

BUILD_INFO.md

@@ -2,27 +2,28 @@
 
 `executorch_wasm_lib.js` and `executorch_wasm_lib.wasm` are the ExecuTorch Wasm
 bindings (`extension/wasm`) with the WebGPU backend, linked into one web bundle.
+The `.js` loader ships in this folder. The `.wasm` is hosted on Hugging Face
+(`executorch-community/ExecuTorch-WebGPU-Runtime`, pinned in `src/config/runtime.js`),
+downloaded and checked against the sha256 below like a model file.
 Every demo in the playground shares this one runtime (`src/runtime/executorch.js`).
 The JS file defines `createExecuTorch()`. After `await et.initWebGPU()`, a `.pte`
 loads with `et.Module.load(path)` and `loadMethod('forward')`, and runs with an
 async `forward([tensors])`.
 
-## This is a pre-release build: rebuild it from ExecuTorch main
+## Source
 
-It was built from the ExecuTorch source tree of 2026-10-15 (`version.txt` 1.6.0)
-with two changes that are under review upstream and not yet on main:
+Built from the ExecuTorch source tree of 2026-10-16 (`version.txt` 1.6.0) with the two
+changes that make WebGPU run in the Wasm build, both merged upstream:
 
-1. **WebGPU in the Wasm build.** The `EXECUTORCH_BUILD_WASM_WEBGPU` option, which
-   links the WebGPU backend into `extension/wasm`, and the `initWebGPU()` binding.
-2. **Resize propagation fix.** `WebGPUGraph::propagate_resize` now resizes every
-   operand before its consumer in one pass. Without it, a multi-token LLM prefill
-   (`tokens` of shape `[1, n]` with 1 < n < 512) fails with
-   `add(resize): operands are not broadcast-compatible`.
+1. pytorch/executorch#23938: the `EXECUTORCH_BUILD_WASM_WEBGPU` option, which links the
+   WebGPU backend into `extension/wasm`, and the `initWebGPU()` binding.
+2. pytorch/executorch#23914: `WebGPUGraph::propagate_resize` resizes every operand before
+   its consumer in one pass, so a multi-token LLM prefill works.
 
-Once both have landed, rebuild from main with the commands below and replace both
-files. The emdawnwebgpu override (`EXECUTORCH_WEBGPU_EMDAWNWEBGPU_PORT`) was only
-needed because the build machine could not reach GitHub. Drop it, and Emscripten
-downloads the same emdawnwebgpu version itself.
+A build from ExecuTorch main that contains both, with the commands below, should give the
+same files. The emdawnwebgpu override (`EXECUTORCH_WEBGPU_EMDAWNWEBGPU_PORT`) was only
+needed because the build machine could not reach GitHub; without it, Emscripten downloads
+the same emdawnwebgpu version itself.
 
 ## Toolchain